library(tidyverse)
library(here)
library(spotifyr)
theme_set(theme_bw())
Considerando algumas das boybands mais famosas ao longo dos anos, elas apresentam um mesmo molde? Ou seja, a mesma média de tempo / energia / etc?
Boybands são bandas formadas geralmente por meninos adolescentes, e tem como objetivo conquistar o público de meninas adolescentes. O estilo musical é bem característico, com músicas animadas e dançantes, e algumas baladas. Iremos analisar as principais músicas de várias boybands presentes no Spotify, entre elas as clássicas NSYNC e Backstreet Boys, além do fenômeno kpop BTS. Queremos saber se há um padrão nas características de Tempo, Dançabilidade, Valência e Energia. Tempo é a velocidade ou ritmo de uma música e é medido em batidas por minuto (BPM); Dançabilidade descreve como uma música é adequada para a dança baseada em uma combinação de elementos musicais (quanto mais próximo de 1, mais dançante); Valência mede a positividade da faixa (alta Valência significa mais positiva (por exemplo, felizes, alegres, eufóricas), enquanto baixa valência significa mais negativa (por exemplo, triste, deprimido, zangado); Energia é uma medida de 0 a 1 e representa uma medida de intensidade e atividade. A playlist base pode ser encontrada em: https://open.spotify.com/user/gabimotta15/playlist/47WfTEyFNe64N1OxeQ7xbo?si=g93Ia7niTlKYnjJlrn7dQA
boybands = read_csv(here("data/playlist-boybands.csv"))
Parsed with column specification:
cols(
danceability = col_double(),
energy = col_double(),
key = col_character(),
loudness = col_double(),
mode = col_character(),
speechiness = col_double(),
acousticness = col_double(),
instrumentalness = col_double(),
liveness = col_double(),
valence = col_double(),
tempo = col_double(),
track_uri = col_character(),
duration_ms = col_double(),
time_signature = col_integer(),
key_mode = col_character(),
track_name = col_character(),
album_name = col_character(),
artist = col_character()
)
sumarios = boybands %>%
group_by(artist) %>%
summarise(media_tempo = mean(tempo), media_energia = mean(energy), media_danca = mean(danceability), media_valencia = mean(valence))
b = sumarios %>%
ggplot(aes(y = artist)) +
geom_point(aes(x = media_energia, color = "Energia")) +
geom_point(aes(x = media_danca, color = "Dançabilidade")) +
geom_point(aes(x = media_valencia, color = "Valência")) +
labs(x = "Médias dos Atributos", y = "Artista" , color = "Atributo")
plotly::ggplotly(b)
We recommend that you use the dev version of ggplot2 with `ggplotly()`
Install it with: `devtools::install_github('hadley/ggplot2')`
A maioria das boybands apresenta média de Energia acima de 0.7, e a média de Dançabilidade entre 0.5 e 0.7. Apenas a Valência se destaca, tendo bandas muito positivas como Menudo (quase 0.8 de Valência), e bandas muito negativas como The Wanted (abaixo de 0.4).
p = boybands %>%
mutate(faixa = paste(track_name, album_name)) %>%
ggplot(aes(x = tempo,
color = artist,
label = faixa,
y = danceability)) +
geom_point(size = .8, alpha = .8)
plotly::ggplotly(p)
We recommend that you use the dev version of ggplot2 with `ggplotly()`
Install it with: `devtools::install_github('hadley/ggplot2')`
Lady Gaga possui álbuns de vários estilos, o Tempo varia muito para cada álbum?
Lady Gaga é uma artista muito talentosa, ganhou vários prêmios com seus álbuns, que vão do pop ao jazz. Como é o comportamento do Tempo nesses álbuns? Tempo é a velocidade ou ritmo de uma música e é medido em batidas por minuto (BPM). Como os estilos musicais mudam, é esperado que haja uma variação nesse Tempo. Para essa análise serão desconsiderados singles e álbuns promocionais. A playlist base pode ser encontrada em: https://open.spotify.com/user/gabimotta15/playlist/7pH3kwz0vVTgmKt2cR7Z9o?si=JcvkobZXSkKBCE13ubsM7w
gaga = read_csv(here("data/playlist_gaga.csv"))
mlabels <- c("ARTPOP","Born This Way", "Cheek to Cheek", "Joanne", "The Fame", "The Fame Monster")
g = gaga %>%
mutate(faixa = paste(track_name)) %>%
ggplot(aes(x = album_name,
label = faixa,
y = tempo)) +
geom_point(size = .8, alpha = .8) +
labs(x = "Álbum", y = "Tempo (BPM)", color="Álbum") +
scale_x_discrete(labels=mlabels)
plotly::ggplotly(g)
We recommend that you use the dev version of ggplot2 with `ggplotly()`
Install it with: `devtools::install_github('hadley/ggplot2')`
Podemos perceber que os Tempos estão geralmente concentrados entre 100 e 140 BPM, mas existe uma dispersão maior nos álbuns Cheek to Cheek e Joanne, que são os álbuns de estilos mais diferentes dos outros. Portanto o Tempo não varia muito entre os álbuns mais pop, apenas nos álbuns de jazz e country.
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